Defense Strategies Toward Model Poisoning Attacks in Federated Learning: A Survey
Open accessAbstract
Advances in distributed machine learning can empower future communications and networking. The emergence of federated learning (FL) has provided an efficient framework for distributed machine learning, which, however, still faces many security challenges. Among them, model poisoning attacks have a significant impact on the security and performance of FL. Given that there have been many studies focusing on defending against model poisoning attacks, it is necessary to survey the existing work and provide insights to inspire future research. In this paper, we first classify defense mechanisms for model poisoning attacks into two categories: evaluation methods for local model updates and aggregation methods for the global model. Then, we analyze some of the existing defense strategies in detail. We also discuss some potential challenges and future research directions. To the best of our knowledge, we are the first to survey defense methods for model poisoning attacks in FL.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Poisoning attacks can significantly impact global models, and malicious attackers can prevent global models from converging or manipulate the prediction results of global models.
“Among them, poisoning attacks can significantly impact global models, and malicious attackers can prevent global models from converging or even manipulating the prediction results of global models.”
From Poisoning attacks in federated learning: A survey (2023) · cites this paper as [12]
The citation lists haven’t been fetched yet
References 34 · Cited by 41
- Authors
- Wang, Z., Kang, Q., Zhang, X., & Hu, Q.
- Affiliations
- Indiana University – Purdue University Indianapolis (US)
- Indiana University-Purdue University,Department of Computer and Information Science,Indianapolis,Indiana,USA
- Purdue University West Lafayette (US)
- Venue
- 2022 IEEE Wireless Communications and Networking Conference (WCNC)
- Publisher
- IEEE
- Published
- 2022-04-10
- Pages
- 548-553
- ISSN
- 1525-3511 (ISSN-L)
- OpenAlex
- W4221145471
- Cited by
- 41
- References
- 34
- Citations by year
- 2026: 8 · 2025: 13 · 2024: 15 · 2023: 4 · 2022: 1
- FWCI
- 4.56
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Wireless Communications and Networking Conference (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- IUScholarWorks (Indiana University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (2105004)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Keywords
- federated learning, model poisoning, defense mechanisms, model aggregation, adversarial attacks
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
